Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44863
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .:.:.:.:.:.:.:.:
    -0.10
     Wik
    -0.09
     Markus
    -0.09
     Lightning
    -0.09
    TINGS
    -0.09
    èŀº
    -0.08
    _tol
    -0.08
     SetProperty
    -0.08
     Crane
    -0.08
     Hut
    -0.08
    POSITIVE LOGITS
    ry
    0.09
     sne
    0.09
    ッ
    0.09
     virt
    0.09
    emain
    0.09
     tabi
    0.09
    æķ£
    0.09
    enna
    0.09
     Sheldon
    0.09
    -deals
    0.08
    Activations Density 0.020%

    No Known Activations